Case Study: Insurance Fraud

5th May, 2015

KeyLines has been used to deploy sophisticated network visualization capability in many high profile and complex organizations. In 2013, we helped one of the world’s biggest insurance companies enhance their SAS fraud discovery and analysis solution with a custom-built KeyLines GUI.

Our customers

Our customer was the Canadian branch of a global insurance organization. With over three million customers, they are one of the largest insurers in Canada and take a proactive and best practice approach to detecting and combating fraud.

The problem

Our customer, like many in the insurance industry, uses the SAS suite of tools for fraud detection, prevention and management.

Part of this suite is a Social Network Analysis (SNA) module, which ingests data (at an account, customer, claim and policy level) and presents it as a visual network graph using links and nodes. Users, who are often statisticians, analyze this graph to identify and understand unusual links or behaviors within their data.

For our customer, the SNA module met a vital need to understand connections and patterns in their data, but suffered from several limitations:

  • Inflexibility – the SNA module had limited customizability, especially in terms of defining the user interface. This made it harder to control how users explored the data and limited their capacity to find patterns and, ultimately, discover fraud.
  • Inaccessibility – Data could be called, scored and presented SAS, but users found it difficult to query their data once in the SNA system. In order to expand, move or exclude certain nodes, users would need to formulate and submit a new query, making it difficult to carry out investigations and answer ‘what-if’ questions. SAS is primarily designed for data scientists and statisticians – this limited its value and usefulness as an application for fraud investigators.
  • Limited filtering – our customer needed to apply various filters to their charts to help with the discovery of patterns and frauds. This was not possible in the SAS SNA module.

The requirements

In October 2012, our customer approached Cambridge Intelligence to investigate the KeyLines network visualization software. It was essential to have a solution that could fit seamlessly into the existing web-based SAS applications and data warehouses.

Of their network visualization solution, our customer required the following features:

  • Interactivity – the charts created needed high levels of interactivity, for data exploration and investigation and to help answer the vital ‘what-if’ questions.
  • Easy querying – users needed to be able to easily submit new data queries in an intuitive and simple way.
  • Flexibility and customization – being able to define the user interface, as well as what happened when a user interacts with a chart, was essential.
  • Unbreakable and secure – most importantly, the solution needed to maintain absolute data security and be impossible for the end users to break.

The solution

Early in 2013, our customers decided to begin a two month trial of the KeyLines toolkit. Their research and development department, assisted by support from the KeyLines team, were able to build a network visualization application that added the required functionality to their SAS solution.

Following this trial, KeyLines was selected as the preferred solution and rolled out to the wider fraud team.

The application

The application uses the existing SAS data warehouses and entity profiling (intelligent risk scoring and flagging) to create an interactive KeyLines link chart. This KeyLines chart is securely made available to end users via a web browser.

Using KeyLines’ flexible event model (whereby developers can define what happens each time a user interacts with something, e.g. clicks, right clicks or hovers on a node), a completely customized interface and experience was built. This level of granular development control ensured the whole application was intuitive, easy to use and difficult to break.

KeyLines also simplified the data querying and exploration process. Instead of manually formulating and submitting a new SAS query each time, users can now use KeyLines as a visual query engine – calling new data to the chart on demand with a click.

Additional functionality previously unavailable in SAS’ own visualizations was also made available to staff. These include filters, social network analysis measures, node manipulation and automatic layouts.

Of the successful deployment, Cambridge Intelligence CEO Joe Parry said:

It’s testimony to the flexibility and robustness of KeyLines that our customer was able to integrate such powerful network visualization so seamlessly. We were able to enhance their existing fraud detection and analysis processes by building on the functionality provided by their SAS system. KeyLines has made understanding and analysing connections in their data so much simpler, faster and effective.”

Find out more

If you would like to know more about how KeyLines could help your fraud systems, or if you’d like to undertake a free trial of KeyLines, please get in touch with us.

| | | | |

Subscribe to our newsletter

Get occasional data visualization updates, stories and best practice tips by email